Solution Architect (DFS) (IN)

HCLTech

8–12 yrs Noida, Hyderabad, Chennai, Bengaluru, Pune Full Time Hybrid (office + remote)
HCLTech logo
Posted : today
Actively hiring

Job description

Lead the technical architecture and end-to-end deployment of enterprise Generative AI and Agentic AI solutions on AWS. This senior role involves being a customer-facing solution architect who codes, driving technical success for strategic clients. Responsibilities include making key architecture and deployment decisions, leading customer workshops, reviewing implementations, ensuring production readiness, and mentoring other engineers.

This position offers a dynamic mix of activities, with approximately 50% dedicated to architecture and technical leadership, 30% to customer engagement, and 20% to engineering oversight and mentoring. The role is instrumental in shaping the technical direction and influencing the platform roadmap.

Responsibilities

Own the complete technical delivery of enterprise Agentic AI deployments, from initial discovery and architecture through production rollout, hypercare, and transition to business-as-usual operations.

Key duties include leading customer discovery sessions, technical workshops, architecture reviews, executive technical discussions, solution demonstrations, Proofs of Concept (POCs), pilots, and production planning.

Design and implement customer-specific AI and AWS architectures leveraging Amazon Bedrock, Amazon Bedrock AgentCore, core AWS services, enterprise data sources, applications, security controls, and operational services. This involves defining agent architectures, integration patterns, and production deployment strategies across a wide range of AWS services.

Drive production readiness by defining criteria for functionality, security, performance, reliability, observability, and governance. Establish a robust customer AgentOps strategy covering telemetry, tracing, logging, metrics, and operational dashboards.

Lead complex troubleshooting and root-cause analysis for production issues. Optimize for reliability, latency, scalability, model performance, and AI cost. Review and establish engineering quality standards for deliverables produced by the team.

Mentor and guide engineers, establish reusable deployment and integration patterns, and contribute to platform roadmap priorities by providing technical feedback to various internal teams.

Qualifications

A strong foundation in Python and software engineering is essential, with the ability to guide production code reviews. Extensive hands-on experience with Generative AI, LLMs, RAG, prompt engineering, tool calling, evaluation, and multi-agent architectures is required.

Proficiency with Amazon Bedrock and/or Amazon Bedrock AgentCore, along with frameworks like LangGraph, LangChain, or Strands Agents in production environments, is critical. Deep AWS architecture and engineering experience across Amazon Bedrock and core AWS services is also a must.

Significant enterprise integration experience with REST APIs, databases, ITSM platforms, monitoring systems, identity platforms, and customer-specific applications is expected. A thorough understanding of AWS IAM, role-based access, security, and enterprise networking is necessary.

Experience with containerized applications (Docker, ECS/EKS), Lambda, AgentCore Runtime, and production deployment patterns is required. Strong experience in CI/CD, Git, release management, versioning, and production operations, along with observability, tracing, logging, monitoring, and incident management, is crucial.

Familiarity with Responsible AI principles, guardrails, AI security, data protection, and enterprise governance is important. Excellent customer-facing communication skills and the ability to lead architecture discussions with senior technical stakeholders are essential for success in this role.

Essential Skills

PythonSoftware EngineeringGenerative AILLMsRAGPrompt EngineeringTool CallingEvaluationMulti-Agent ArchitecturesAmazon BedrockAmazon Bedrock AgentCoreLangGraphLangChainStrands AgentsAWS ArchitectureAWS ServicesEnterprise IntegrationREST APIsDatabasesITSM PlatformsMonitoring SystemsIdentity PlatformsCustomer-Specific ApplicationsAWS IAMRole-Based AccessOAuthSecrets ManagementAuthenticationAuthorizationEnterprise NetworkingContainerized ApplicationsDockerECSEKSLambdaAgentCore RuntimeProduction Deployment PatternsCI/CDGitRelease ManagementVersioningProduction OperationsObservabilityTracingLoggingMonitoringDebuggingProduction Incident ManagementKnowledge IntegrationAgent Quality MeasurementResponsible AIGuardrailsAI SecurityData ProtectionEnterprise GovernanceCustomer-Facing Communication

Good to Have

OpenTelemetryADOTEnterprise AgentOpsAgent Evaluation PracticesMCPA2AAWS SDKsEnterprise Agent InteroperabilityTerraformInfrastructure-as-CodeAWS Landing ZonesAPI GatewayEventBridgeStep FunctionsSQS/SNSS3CloudWatchVPC EndpointsPrivate ConnectivityServiceNowCloudOpsSREAIOpsInfrastructure AutomationEnterprise OperationsHigh Availability ArchitecturesScalable ArchitecturesSecure Production ArchitecturesPOCsPilotsMVPsProduction RolloutsStrategic Enterprise DeploymentsMulti-Cloud Platforms

Highlights

  • Actively hiring

More Details

RoleSolution Architect (DFS) (IN)
DepartmentSolution Architect, Forward Deployment Engineer
Employment TypeFull Time, Hybrid (office + remote)

About the Company

HCLTech logo

HCLTech

IT Consulting